Artificial Intelligence-Aided Precision Medicine for COVID-19: Strategic Areas of Research and Development
←
→
Page content transcription
If your browser does not render page correctly, please read the page content below
JOURNAL OF MEDICAL INTERNET RESEARCH Santus et al
Viewpoint
Artificial Intelligence–Aided Precision Medicine for COVID-19:
Strategic Areas of Research and Development
Enrico Santus1,2, PhD; Nicola Marino2,3, BSc; Davide Cirillo2,4, PhD; Emmanuele Chersoni5, PhD; Arnau Montagud4,
PhD; Antonella Santuccione Chadha2,6, MD; Alfonso Valencia4,7, PhD; Kevin Hughes8, MD; Charlotta Lindvall9,10,
MD, PhD
1
Division of Decision Science and Advanced Analytics, Bayer Pharmaceuticals, Whippany, NJ, United States
2
The Women's Brain Project, Zurich, Switzerland
3
Department of Medical and Surgical Sciences, Università degli Studi di Foggia, Foggia, Italy
4
Barcelona Supercomputing Center, Barcelona, Spain
5
Department of Chinese and Bilingual Studies, The Hong Kong Polytechnic University, Hong Kong, China (Hong Kong)
6
Biogen International GmbH, Baar, Switzerland
7
Institució Catalana de Recerca i Estudis Avançats, Barcelona, Spain
8
Massachusetts General Hospital, Boston, MA, United States
9
Dana-Farber Cancer Institute, Boston, MA, United States
10
Harvard Medical School, Boston, MA, United States
Corresponding Author:
Davide Cirillo, PhD
Barcelona Supercomputing Center
c/Jordi Girona, 29
Barcelona
Spain
Phone: 34 934137971
Email: davide.cirillo@bsc.es
Abstract
Artificial intelligence (AI) technologies can play a key role in preventing, detecting, and monitoring epidemics. In this paper, we
provide an overview of the recently published literature on the COVID-19 pandemic in four strategic areas: (1) triage, diagnosis,
and risk prediction; (2) drug repurposing and development; (3) pharmacogenomics and vaccines; and (4) mining of the medical
literature. We highlight how AI-powered health care can enable public health systems to efficiently handle future outbreaks and
improve patient outcomes.
(J Med Internet Res 2021;23(3):e22453) doi: 10.2196/22453
KEYWORDS
COVID-19; SARS-CoV-2; artificial intelligence; personalized medicine; precision medicine; prevention; monitoring; epidemic;
literature; public health; pandemic
worldwide. An example is the widely reported algorithm from
Introduction the Canadian company BlueDot, based on natural language
The ongoing COVID-19 pandemic has highlighted the fragility processing (NLP) and machine learning, which forecasted the
of the health care system during unexpected events, testing the emerging risk of a virus spread in Hubei province in late
endurance of even the top-performing ones [1]. As noted by December 2019, by screening news reports and airline ticketing
several scholars, embracing artificial intelligence (AI) for health [3].
care optimization and outcome improvement is not an option Awareness of the benefits of employing AI to support and
anymore [2]. Concerning the ongoing COVID-19 pandemic, manage the COVID-19 crisis and its aftermath is increasing,
several studies have highlighted that the timely inclusion of particularly in the medical and research community. Notable
AI-powered technologies would have accelerated the examples of early AI-powered contributions include the
identification of and effective response to COVID-19 outbreaks discovery of relevant SARS-CoV-2 target proteins by
https://www.jmir.org/2021/3/e22453 J Med Internet Res 2021 | vol. 23 | iss. 3 | e22453 | p. 1
(page number not for citation purposes)
XSL• FO
RenderXJOURNAL OF MEDICAL INTERNET RESEARCH Santus et al
DeepMind’s AlphaFold [4] and the design by Infervision of a The way the AI systems will be exploited is probably the most
computer vision algorithm for the detection of coronavirus delicate topic in this adoption process, particularly if we refer
pneumonia based on lung images [5]. to the decisional independence of the medical staff. As humans,
in fact, clinicians are also affected by numerous cognitive biases,
Benefits do, however, come with technical challenges and
including the confirmation bias, which may lead them to give
related risks that still need to be properly assessed. For example,
excessive importance to the evidence supporting automated
the absence of transparency and interpretability in AI models
prediction (eg, risk prediction, diagnosis, and treatment
obscures the fact that the efficacy of these technologies is not
suggestion) and ignore evidence that refutes it [8,24].
equal across population groups. COVID-19 incidence and
outcomes vary according to a large number of individual factors, Despite the abovementioned concerns, there are numerous
including age, sex, ethnicity, health status, drug utilization, and success stories in the adoption of risk prediction models. For
others [6]. Sensitizing AI technologies to the diversity of the example, Duke University adopted a system called Sepsis Watch
patient population and ensuring data security [7] is imperative that identifies in advance the inflammation leading to
to avoid biased decisions [8-10]. Therefore, a crucial step to sepsis—one of the leading causes of hospital deaths. Within
obtain robust, trustworthy, and intelligible applications that two years from the tool introduction, the number of
account for demographic equity is to assess potential biases in sepsis-induced patients drastically decreased [25], thanks to
the resources used to train AI models for precision medicine three key elements: (1) adaptation of the predictive model to a
[11]. highly specific context; (2) scalability through integration with
hospital workflows; and (3) the adopted user experience–based
As of today, AI systems are, regrettably, rarely endowed with
approach, which places clinicians and health care professionals
robustness to class imbalances, such as sex and gender groups
at the center of the software development process, adhering
[12]. In this regard, sex differences in COVID-19 cases, as well
with the human-in-the-loop paradigm [26,27].
as sex-specific risk factors and socioeconomic burden, have
been recently highlighted in a case study by the European The COVID-19 crisis is accelerating anticipated changes
Commission [13]. Dataset multidimensionality that can fairly towards a stronger collaboration between computer science and
represent the population constitutes one of the main challenges medicine. In particular, the crisis has exposed the need for
for biobanking and cohort design efforts that collect different increased scrutiny of the relationship between AI and patients
axes of health data [14]. In this regard, fair and broad data as well as health care personnel under the lens of human and
collection systems are of primary importance. Two essential emotional needs, as demonstrated by the surge of mental health
international references for COVID-19 genomic and medical consequences of the pandemic [28] and the growing
data are the EMBL-EBI COVID-19 Data Portal [15] and the development of AI-based mental health apps and related digital
NIH National COVID Cohort Collaborative (N3C) [16]. The tools [29]. Such aspects, together with others related to general
COVID-19 Host Genetics Initiative [17] is an international data access and the use of AI for disease outcome prediction,
collaborative undertaking to share resources to investigate the are fueling the current debate about the convergence of AI and
genetic determinants of COVID-19 susceptibility, severity, and medicine [30,31] and the actionable realization of AI-powered
outcomes [18]. The Coronavirus Pandemic Epidemiology innovations to bridge the gap between technological research
(COPE) consortium aims to involve experts in the development and medical practice, including applications in medical triage
of a personalized COVID-19 Symptom Tracker mobile app that and advice, diagnostics and risk-adjusted paneling, population
works as a real-time data capture platform [6], which garnered health management, and digital devices integration [32].
over 2.8 million users in a few days. Moreover, COVID-19 Concerning this aspect, it is important to mention the recent
sex-disaggregated data are collected by Global Health 50/50 publication of guidelines for the rigorous and transparent
[19], an initiative housed at University College London, adoption of AI in the clinical practice: CONSORT-AI
advocating for gender equity. (Consolidated Standards of Reporting Trials–Artificial
Intelligence) [33] and SPIRIT-AI (Standard Protocol Items:
Other ethical concerns include life-or-death decisions through
Recommendations for Interventional Trials–Artificial
risk prediction models, which may help optimize resource
Intelligence) [34].
allocation in times of scarcity. The application of nonoptimal
models may incur the risk of worsening biases and exacerbating Translating patient data to successful therapies is the major
disparities for people with serious illnesses and different objective of implementing AI for health [35], especially in times
treatment priorities, potentially causing the reduction in the use of a pandemic crisis, with the ultimate goal of achieving a
of services rather than achieving the best patient care [20]. successful bench-to-bedside model for better clinical
Nevertheless, the power of prediction models is impressive, and decision-making [36,37]. In this work, we review some major
it may play a key role in the future if properly exploited. For examples of what AI has achieved during the COVID-19
instance, a study from Cambridge University [21] shows how pandemic and the challenges that this technology and the
the use of secure AI operating on anonymized COVID-19 data medical community are currently facing in four main strategic
can accurately predict the patient journey, allowing an optimal areas of research and development (Figure 1): (1) triage,
allocation of resources and enabling well-informed and diagnosis, and risk prediction; (2) drug repurposing and
personalized health care decision-making. This is a particularly development; (3) pharmacogenomics and vaccines; (4) mining
important point, especially considering the difficulty in of the medical literature.
managing the increasing need for intensive care units (ICUs)
during the COVID-19 pandemic peak [22,23].
https://www.jmir.org/2021/3/e22453 J Med Internet Res 2021 | vol. 23 | iss. 3 | e22453 | p. 2
(page number not for citation purposes)
XSL• FO
RenderXJOURNAL OF MEDICAL INTERNET RESEARCH Santus et al
Figure 1. Main strategic areas of research and development for the realization of artificial intelligence (AI) to fight COVID-19: (1) triage, diagnosis,
and risk prediction; (2) drug repurposing and development; (3) pharmacogenomics and vaccines; and (4) mining of the medical literature. The text
within the four panels enlists the advantages and actionable solutions exhibited by the AI-aided precision medicine approaches surveyed in this work.
of two patients will get more benefits from going on a ventilator
Triage, Diagnosis, and Risk Prediction today? The predictive models showed accuracies ranging from
AI has been applied to determine treatment priorities in patients 77% for ventilator need to 83% for ICU admission and 87% for
with COVID-19 or triage and to better allocate limited resources. mortality.
A group of researchers at the General Hospital of the People’s Risk prediction models are not new to the AI-aided health care
Liberation Army (PLAGH), Beijing, China, has developed an approach. They have already been successfully utilized for tasks
online triage tool model [38] to manage suspected COVID-19 such as predicting the risk of developing cancer [41,42] and
pneumonia in adult patients with fever [39]. Using clinical identifying which patients are likely to benefit from heart-related
symptoms, routine laboratory tests, and other clinical procedures [43]. However, the COVID-19 crisis has accelerated
information available at admission (eg, clinical features), they the utilization of such models. In a recent study, Wynants and
trained a model based on logistic regression with the least collaborators [44] screened 14,217 published titles about the
absolute shrinkage and selection operator (LASSO), obtaining pandemic from PubMed and Embase (Ovid, arXiv, medRxiv,
an area under the receiver operating characteristic curve and bioRxiv), finding over 107 studies describing 145 prediction
(AUROC) of 0.841 (100% sensitivity and 72.7% specificity). models. Among them, 4 models aimed to identify people at risk
Based on data from two hospitals in Wenzhou, Zhejiang, China, and 50, to predict the mortality risk, progression to severe
another study group recently used an entropy-based feature disease, ICU admission, ventilation, intubation, or length of
selection approach: they modeled combinations of clinical hospital stay. These models not only provide interesting results
features that could identify initial presentation patients who are but also inform about the most valuable predictors, such as age,
at a higher risk of developing severe illness, with an accuracy body temperature, lymphocyte count, and lung imaging features.
of 80% [40]. Their results show that mildly elevated alanine Despite this, these models cannot be directly applied in the
aminotransferase levels, the presence of myalgias (body aches), clinical setting without further validation, in order to guarantee
and an elevated hemoglobin level (red blood cells), in this order, data and experiment transparency and robustness, together with
are predictive of the later development of acute respiratory decision interpretability and model generalizability.
distress syndrome.
The remaining 91 models from this study were dedicated to the
A thorough study on risk prediction was carried out at the diagnosis of COVID-19, 60 of which exploited medical imaging.
University of Cambridge based on the development of a proof This number clearly shows that diagnosis is another important
of concept system to model the full patient journey through risk field for the application of AI techniques [45], with digital
prediction models [21]. By identifying the risk of mortality and pathology exhibiting high effectiveness. In particular,
ICU/ventilator need, the system aims at enabling doctors to convolutional neural networks (CNNs) have been supporting
answer questions such as: Which patients are most likely to radiologists in their expert decisions [46]. In a recent study, a
need ventilators within a week? How many free ICU beds in CNN was trained to automatically learn patterns related to
the hospital are we likely to have in a week from now? Which COVID-19 (ie, ground-glass opacities, multifocal patchy
https://www.jmir.org/2021/3/e22453 J Med Internet Res 2021 | vol. 23 | iss. 3 | e22453 | p. 3
(page number not for citation purposes)
XSL• FO
RenderXJOURNAL OF MEDICAL INTERNET RESEARCH Santus et al
consolidation, and/or interstitial changes with a predominantly drug repurposing [52] and approaches for drug development,
peripheral distribution), achieving an AUROC of 0.996 (98.2% including de novo drug design [53].
sensitivity and 92.2% specificity) and outperforming the
Drug repurposing comprises identifying existing drugs that
reverse-transcription polymerase chain reaction, which also
could effectively act on proteins targeted by the virus. Recently,
suffers from a significant time lag. In addition to accuracy, these
332 high-confidence SARS-CoV-2 protein–human protein
approaches put the speed of the diagnosis on the table: CNNs
interactions have been experimentally identified, as well as 69
can analyze up to 500 images in a few seconds, whereas
ligands, comprising drugs approved by the US Food and Drug
radiologists would need hours to complete the same task.
Administration (FDA) and compounds in preclinical and clinical
Although chest computed tomography (CT) scans represent a trials, which specifically target these interactions [54].
commonly exploited source of information to train AI to rule Understanding which proteins and pathways in the host the
out SARS-CoV-2 infection, the rapid detection of patients with virus targets during infection is crucial for the development of
COVID-19 can greatly benefit from learning approaches that AI systems for drug repurposing.
utilize heterogeneous types of data. In this regard, it is crucial
For instance, algorithms modeling the interaction between drugs
to consider the importance of training CNNs in a correct gender
and proteins have helped identify baricitinib, which was
balance in medical imaging datasets to avoid producing distorted
previously used for the treatment of arthritis, as a useful drug
classifications for assisted diagnosis [12]. Moreover, it is crucial
against COVID-19 [55]. This drug inhibits the proteins that
to rely on high-quality benchmarking and robust validation
help the virus penetrate the host cell. Thanks to approaches that
strategies to assess the generalization of the model to other
exploit the computational identification of relations between
datasets and populations [47,48].
existing drugs and target molecules, research published by a
Indeed, AI can exploit multidimensional data, including the team of Korean and American scientists has allowed the
series of epidemiological, clinical, biological, and radiological identification of FDA-approved antivirals that could potentially
criteria defined by the World Health Organization [49]. In a target the key proteins for COVID-19 [56].
collaboration between researchers at hospitals in China and in
The molecular processes of virus-host interactions have been
the USA, CNN and other machine learning methods (eg, support
recently reconstructed in an international effort coordinated by
vector machine, random forest, and neural networks) have been
domain experts, called the COVID-19 Disease Map project
used to model and integrate CT scans and clinical information
[57]. The project aims to maintain an open-access resource for
for diagnostic purposes [45]. The joint model that uses both
continuous, curated integration of data and knowledge bases to
information sources achieved a 0.92 AUROC (84.3% sensitivity
support computational analysis and disease modeling. It
and 82.8% specificity), outperforming the individual models.
represents a milestone of paramount importance for the
Moreover, the models allowed the identification of age, viral
development of AI systems for SARS-CoV-2 and their
exposure, fever, cough, cough with sputum, and white blood
comparison with models of other coronaviruses. Moreover, by
cell counts as the main features associated with SARS-CoV-2
providing information about the intermolecular wiring of
infection status.
virus-host interactions, the project enables network-based AI
Recently, the National Institute of Biomedical Imaging and modeling for COVID-19 drug repurposing, which has recently
Bioengineering has launched the Medical Imaging and Data shown promising results by using network diffusion and network
Resource Center with the goal of coupling AI and medical proximity [58]. Moreover, deep neural networks largely
imaging for COVID-19 early detection and personalized employed in NLP, such as the Transformer architecture, have
therapies [50]. also been proposed for COVID-19 drug repurposing [56].
AI has also been utilized to identify patients at higher risk of In the field of drug development, that is, the
mortality. Researchers at the Tongji Hospital, Wuhan, China, pharmacotherapeutic course of a newly identified lead
have screened electronic health records of 375 discharged compound, computational models have been proven extremely
patients to use clinical measurements as features and have successful in facilitating a quicker, cheaper, and more effective
trained a gradient-boosted decision tree model to predict development of new drugs [59]. For instance, AI can map
mortality risk [51]. The accuracy of the system was 93%. Its multidimensional characteristics of proteins to considerably
utilization would make it possible for physicians to immediately speed up the research process in comparison to traditional
identify critical cases and act accordingly. The model was also methodologies such as x-ray crystallography. In this regard, AI
able to detect three key clinical features, that is, lactic is crucial in optimizing drug discovery pipelines and improving
dehydrogenase, lymphocyte count, and high-sensitivity drug development outcomes, with estimated costs of US $2.6
C-reactive protein. billion [59].
Structural modeling and chemoinformatics methods for
Drug Repurposing and Development COVID-19 (eg, docking-based binding conformation studies
Although triage, diagnosis, and risk prediction are three of the of small molecules to target human or viral proteins) can greatly
most relevant tasks that AI has helped with during the peaks of benefit from AI solutions. For instance, AI-based approaches
the pandemic, other objectives are currently being addressed have been used to infer structural similarities among molecules,
for long-term solutions. Among them are target selection for such as algorithms that can model the graphical structure of
chemical compounds through graph convolutional networks or
other approaches [60]. AI systems can also leverage knowledge
https://www.jmir.org/2021/3/e22453 J Med Internet Res 2021 | vol. 23 | iss. 3 | e22453 | p. 4
(page number not for citation purposes)
XSL• FO
RenderXJOURNAL OF MEDICAL INTERNET RESEARCH Santus et al
about protein sequences to infer the activity of similar ones. As Population genetics is also needed to better understand the
previously mentioned, Google DeepMind has managed to association between genetic variability and COVID-19. The
predict the structure of five proteins targeted by SARS-CoV-2, importance and complexity of population genetic information,
namely SARS-CoV-2 membrane protein, Nsp2, Nsp4, Nsp6, such as genome-wide association studies (GWAS), for drug
and papain-like proteinase (C-terminal domain) [4]. The deep discovery are exemplified by a study showing that 8% of drugs
learning approach uses amino acid features from similar approved by the FDA target molecules with genetic support,
sequences, based on multiple sequence alignment, to infer the whereas only 2% of phase-1 drugs are genetically supported
distribution of structural distances to predict the protein [73]. Despite such low rates, GWAS can help identify
structures [61]. therapeutics that can be repurposed to treat individuals affected
by diseases that are mechanistically related to those for which
Finally, AI can also be used to synthetically generate new
the drugs were developed [74]. Insights from GWAS can also
molecules, such as new chemical compounds. For instance, the
inform about better patient management and therapy, such as
biotech company Insilico Medicine used reinforcement learning
the case of variants in six genes on chromosome 3, namely
to model small molecules and identify those that inhibit specific
SLC6A20, LZTFL1, CCR9, FYCO1, CXCR6, and XCR1, which
infection pathways. The team created a generative chemistry
have been recently associated with severe COVID-19 cases
pipeline to design novel SARS-CoV-2 inhibitors to later be
with respiratory failure [75].
synthesized and tested. The pipeline employs a large array of
generative models, including autoencoders, generative Understanding population genetic heterogeneity is crucial for
adversarial networks, and genetic algorithms optimized with vaccine design, in particular, as it concerns the individual
reinforcement learning [53]. variability of the major histocompatibility complex (MHC-I
and MHC-II) proteins, encoded by the HLA gene, which present
Pharmacogenomics and Vaccines SARS-CoV-2 epitopes to the immune system. Such individual
variability, coupled with the importance of cellular immunity
Pharmacogenomics, which is the study of the role of genomic in the severity of the response to the infection, makes the
characteristics of an individual in drug response, represents a identification of actionable targets for COVID-19 vaccines a
key gateway to personalized medicine [62-64]. Although the challenging endeavor. AI models for COVID-19 vaccine
translation of genomic information into clinical practice is development focus on the prediction of potential epitopes by
recognized as one of the most challenging aspects of the future using a variety of techniques, such as deep docking [76], long
of medicine [65], the information about the genetic makeup of short-term memory networks [77], extreme gradient boosting
individual patients has the potential to guide clinical decision [78], as well as approaches that account for different HLA alleles
support and to facilitate biomedical research in many different by combining several existing machine learning tools [79]. A
areas. For instance, genomics can inform drug discovery by recent survey of AI-based approaches to COVID-19 vaccine
providing simultaneous insights into the disease mechanisms design [80] suggests that the most popular candidate is the
and potential targets for treating individual patients [66]. SARS-CoV-2 spike protein, which initiates the interaction with
Pharmacogenomics approaches to COVID-19 are still in their the host through the attachment to the ACE2 receptor [81].
infancy. Indeed, although the SARS-CoV-2 genome was
published in draft on January 10, 2020 [67], and real-time Mining of the Medical Literature
tracking of the pathogen evolution is now available [68], much
The staggering rate of publications about COVID-19, both in
less genomic information is currently available about the host.
the form of preprints and peer-reviewed articles, is posing
Several studies focus on genetic variations associated with
unprecedented challenges to knowledge acquisition and the
susceptibility to infection and clinical manifestations, including
information quality assessment process. A large part of content
human leukocyte antigen (HLA) variants in the UK Biobank
is produced by humans for humans, in the form of free text,
population-based cohort [69] and angiotensin-converting enzyme
where crucial pieces of information end up being buried.
2 (ACE2) variants in the Italian population [70]. Retrospective
Because free text is not intelligible by machines, human
and prospective studies focusing on COVID-19 disease
intervention must identify the relevant pieces of information
susceptibility and severity have been collected by the COVID-19
from the publications and turn it into a tabular form. Recent
Host Genetics Initiative [17,18].
developments in NLP techniques have helped the automation
Despite the absence of direct evidence of pharmacogenomics of this process through machine learning and, in particular, deep
data in COVID-19 patients, the related literature for COVID-19 learning algorithms [82,83]. Symptoms, patient demographics,
therapies, including hydroxychloroquine, ribavirin, and clinical data, algorithms, performance, and limitations are
baricitinib, has been recently surveyed [71]. Potential actionable identifiable in the texts by properly trained models, which can
genetic markers have been reported, namely, several genetic obtain comparable accuracy to humans at a much faster rate,
variants that can alter the pharmacokinetics of drugs that may making it finally possible to monitor the enormous volume of
affect the response to COVID-19 treatments. Importantly, as the literature produced [84]. The resulting structured data can
age, race, gender, and comorbidities have been associated with be exploited to enrich knowledge graphs (KGs) [85-87], which
COVID-19 risk [72], these factors are deemed warranted to provide a means to represent and formalize information [85,88],
assess their role in the variation of treatment responses and need analytical, relational, and inferential investigations and fill the
further investigation. knowledge gaps in the community. Moreover, to rationalize the
immense quantity of information on COVID-19, new algorithms
https://www.jmir.org/2021/3/e22453 J Med Internet Res 2021 | vol. 23 | iss. 3 | e22453 | p. 5
(page number not for citation purposes)
XSL• FO
RenderXJOURNAL OF MEDICAL INTERNET RESEARCH Santus et al
can generate low-dimensional representations of the KGs, We list here representative KG efforts that have been directed
allowing researchers for clustering and classification [85,89]. at the fight against COVID-19 (see Textbox 1).
Textbox 1. Knowledge graph resources for COVID-19.
Project names and references:
• KG-Covid-19 Knowledge Graph Hub [90]
• COVID-19 Community Project [91]
• COVID-KG [92]
• CovidGraph [93]
• COVID-19 Miner [94]
• COVID-19 Biomedical Knowledge Miner [95]
• COVID-19 Taxila [96]
The KG-Covid-19 Knowledge Graph Hub project is the first trials, and other relevant sources to enable users to search and
Knowledge Graph Hub (KG-Hub) [90] dedicated to COVID-19. analyze the COVID-19 literature. Publications and data are
KG-Hub is a software to download and transform data to a automatically updated.
central location for building KGs from different combinations
of data sources. The Covid-19 KG-Hub downloads and Discussion
transforms data from more than 50 different COVID-19
databases of drugs, genes, proteins, ontologies, diseases, The COVID-19 pandemic has caused some of the most
phenotypes, and publications and generates a KG that can be significant challenges that national health care systems have
used for machine learning. had to face in recent human history. These systems include not
only hospitals but also a multitude of clinicians, retirement and
The COVID-19 Community Project [91] is a community-based nursing homes, families, and communities. Government
KG that links heterogeneous datasets about COVID-19, in three lockdown policies undertaken to reduce hospital strain has
main areas: the host, the virus, and the cellular environment. impacted the society as a whole and has also had social and
These KGs use several publicly available datasets, such as the economic consequences, which have been more severe for
CORD-19 dataset, a set of over 51,000 scholarly articles about minorities and vulnerable groups [101]. Moreover, this pandemic
coronaviruses [97]. is taking place in the age of social media and Web 2.0, which
Other notable databases used in KGs are the COVID-19 Data contain plenty of misinformation and fake news, and with no
Portal (see Introduction) and The COVID-19 Drug and Gene way for the average internet user to check the reliability of the
Set Library [98]. One of the tools that use these is the sources. Nevertheless, the COVID-19 crisis has also shown the
COVID-KG [92], which embeds entities in the KG, such as promise of technology in facilitating a better understanding of
papers, authors, or journals [99]. a complex disease and its impact on public health.
CovidGraph [93] is a collaboration of researchers to build a Here, we illustrated examples of how AI can advance research
research and communication platform that encompasses over and clinical medicine and prepare governments for future similar
40,000 publications, case statistics, genes and functions, crises. AI shows promise to deliver models for outbreak
molecular data, and much more. The output is a KG in which analytics and detection, prevention, early intervention, and
entity relationships can be found and new pieces of literature decision-making. We highlighted the unparalleled opportunity
can be discovered. Another tool that uses the CORD-19 dataset for AI to fill the gap between translational research and clinical
is COVID-19 Miner [94], which provides access to a database medicine. Finally, in addition to the medical applications of AI,
of interactions among genes or proteins, chemicals, and it is worth mentioning the potential of NLP for monitoring the
biological processes related to SARS-CoV-2, which are quality of the information available to the public and fighting
automatically extracted using NLP from the CORD-19 dataset fake news [102-104].
and manuscripts updated daily from the preprint servers Thanks to the availability of big data and high-performance
medRxiv and bioRxiv [100]. computing, the fight against the novel coronavirus can leverage
Furthermore, COVID-19 Biomedical Knowledge Miner [85,95] the support of AI, as demonstrated by initiatives such as the
is an intent to lay the foundation for a comprehensive and COVID-19 High Performance Computing Consortium [105].
interactive KG in the context of COVID-19 that connects the This technology allows us to address, at a much higher speed
causes and effects and enables users to completely explore the and a comparable performance, complex tasks that cannot be
information contained therein. Data are supplied from papers executed by humans—who can now focus on more
available in PubMed and preprints available from platforms intelligence-demanding activities such as emotional intelligence
such as bioRxiv, chemRxiv, medRxiv, PrePrints, and Research and human-to-human bonding [106].
Square. Lastly, COVID-19 Taxila [96] is an AI and NLP system
that uses thousands of COVID-19–related publications, clinical
https://www.jmir.org/2021/3/e22453 J Med Internet Res 2021 | vol. 23 | iss. 3 | e22453 | p. 6
(page number not for citation purposes)
XSL• FO
RenderXJOURNAL OF MEDICAL INTERNET RESEARCH Santus et al
Although AI is traditionally trained on large datasets for With this approach, AI can predict the risk of an individual to
identifying population-level patterns (ie, common characteristics develop a disease and estimate the likelihood of success for a
among people belonging to some clinical classes), recent efforts treatment. In the case of COVID-19, this could lead to a better
have promoted the utilization of this technology in conjunction allocation of resources and an improved match between
with the principles of precision medicine, to substitute the treatments and patients, consequently improving outcomes for
“average patient” [42] with a real individual, based on preventive and therapeutic interventions. Therefore, AI-aided
geographical and socioeconomic signature as well as genetic, precision medicine connects some of the key benefits for a
epigenetic, and other molecular profiles [107]. Under this sustainable and effective health care system: efficiency, efficacy,
paradigm, AI is meant to empower clinicians to tailor and safety assessment [30].
interventions [108] (whether preventive or therapeutic) to the
AI is recognized as a necessity to achieve precision medicine
nuanced—and often unique—features of every human being
in COVID-19. The current crisis has highlighted that a huge
[109]. To this end, multidimensional datasets, such as the variety
amount of work is still needed to exploit AI-based solutions to
of data modalities that are currently collected and modeled for
their full potential in order to transform health care. AI
COVID-19 [110-112], capture individual genetic, biochemical,
implementation in the clinical setting is still far from completion
physiological, environmental, and behavioral variations [113]
[115]. The highly fragmented and diverse health care systems,
that may interfere with the development, progression, and
absence of a protocol for documenting patient data, ethical
treatment of a disease. Thanks to the drop in price of sequencing
constraints (such as privacy), and limitations of AI itself (eg,
the human genome (from billions to hundreds of dollars in 30
bias and non-interpretability) still represent serious challenges
years [114]), it is now possible to exploit AI to study phenotypic,
to extensive AI adoption [116].
genotypic, and environmental correlations among diseases [115].
Acknowledgments
We are deeply thankful to the Women’s Brain Project (WBP) (www.womensbrainproject.com), an international organization
advocating for women’s brain and mental health through scientific research, debate, and public engagement. The authors would
like to thank Maria Teresa Ferretti and Shahnaz Radjy for the helpful comments. DC, AM, and AV have received funding from
the European Commission’s Horizon 2020 Program H2020-SC1-DTH-2018-1, “iPC-individualizedPaediatricCure” (ref. 826121),
and H2020-ICT-2018-2, “INFORE-Interactive Extreme-Scale Analytics and Forecasting” (ref. 825070).
Authors' Contributions
ES and NM conceived the study with the contribution of ASC, EC, and DC. ES and NM directed the content selection and design,
assisted by EC, DC, and AM. AV, KH, and CL supervised the project. The corresponding author had the final responsibility for
the decision to submit the manuscript for publication. All authors have contributed to the writing and editing of the manuscript
and have read and approved the final manuscript.
Conflicts of Interest
ASC and ES are currently employees at Biogen International GmbH, HQ, Switzerland, and Bayer Pharmaceuticals, USA,
respectively. The other authors declare no competing interests. KH is a founder and owns equity of CRA Health (formerly Hughes
RiskApps), is co-creator of Ask2Me.Org, which is licensed for commercial use by the Dana-Farber Cancer Institute, and receives
honoraria from Myriad Genetics.
References
1. Legido-Quigley H, Asgari N, Teo YY, Leung GM, Oshitani H, Fukuda K, et al. Are high-performing health systems resilient
against the COVID-19 epidemic? The Lancet 2020 Mar;395(10227):848-850. [doi: 10.1016/S0140-6736(20)30551-1]
2. McCall B. COVID-19 and artificial intelligence: protecting health-care workers and curbing the spread. The Lancet Digital
Health 2020 Apr;2(4):e166-e167. [doi: 10.1016/s2589-7500(20)30054-6]
3. Niiler E. An AI Epidemiologist Sent the First Alerts of the Coronavirus Internet. Wired. 2020 Jan 25. URL: https://www.
wired.com/story/ai-epidemiologist-wuhan-public-health-warnings/ [accessed 2020-07-07]
4. Computational predictions of protein structures associated with COVID-19 Internet. DeepMind. URL: https://deepmind.
com/research/open-source/computational-predictions-of-protein-structures-associated-with-COVID-19 [accessed 2020-07-07]
5. Lan L, Xu D, Ye G, Xia C, Wang S, Li Y, et al. Positive RT-PCR test results in patients recovered from COVID-19. JAMA
2020 Apr 21;323(15):1502-1503 [FREE Full text] [doi: 10.1001/jama.2020.2783] [Medline: 32105304]
6. Drew DA, Nguyen LH, Steves CJ, Menni C, Freydin M, Varsavsky T, COPE Consortium. Rapid implementation of mobile
technology for real-time epidemiology of COVID-19. Science 2020 Jun 19;368(6497):1362-1367 [FREE Full text] [doi:
10.1126/science.abc0473] [Medline: 32371477]
7. Shaban-Nejad A, Michalowski M, Buckeridge DL. Health intelligence: how artificial intelligence transforms population
and personalized health. NPJ Digit Med 2018;1:53 [FREE Full text] [doi: 10.1038/s41746-018-0058-9] [Medline: 31304332]
8. Challen R, Denny J, Pitt M, Gompels L, Edwards T, Tsaneva-Atanasova K. Artificial intelligence, bias and clinical safety.
BMJ Qual Saf 2019 Mar;28(3):231-237. [doi: 10.1136/bmjqs-2018-008370] [Medline: 30636200]
https://www.jmir.org/2021/3/e22453 J Med Internet Res 2021 | vol. 23 | iss. 3 | e22453 | p. 7
(page number not for citation purposes)
XSL• FO
RenderXJOURNAL OF MEDICAL INTERNET RESEARCH Santus et al
9. Parikh RB, Teeple S, Navathe AS. Addressing bias in artificial intelligence in health care. JAMA. Epub ahead of print
posted online on November 22, 2019 2019. [doi: 10.1001/jama.2019.18058] [Medline: 31755905]
10. Nelson GS. Bias in artificial intelligence. N C Med J 2019;80(4):220-222 [FREE Full text] [doi: 10.18043/ncm.80.4.220]
[Medline: 31278182]
11. Cirillo D, Catuara-Solarz S, Morey C, Guney E, Subirats L, Mellino S, et al. Sex and gender differences and biases in
artificial intelligence for biomedicine and healthcare. NPJ Digit Med 2020 Jun 01;3(1):81 [FREE Full text] [doi:
10.1038/s41746-020-0288-5] [Medline: 33597695]
12. Larrazabal AJ, Nieto N, Peterson V, Milone DH, Ferrante E. Gender imbalance in medical imaging datasets produces biased
classifiers for computer-aided diagnosis. Proc Natl Acad Sci U S A 2020 Jun 09;117(23):12592-12594 [FREE Full text]
[doi: 10.1073/pnas.1919012117] [Medline: 32457147]
13. The impact of sexgender in the COVID-19 pandemic Internet. European Commission. 2020. URL: https://ec.europa.eu/
info/publications/impact-sex-and-gender-covid-19-pandemic_en [accessed 2020-07-07]
14. Shilo S, Rossman H, Segal E. Axes of a revolution: challenges and promises of big data in healthcare. Nat Med 2020
Jan;26(1):29-38. [doi: 10.1038/s41591-019-0727-5] [Medline: 31932803]
15. COVID-19 Data Portal. URL: https://www.covid19dataportal.org/ [accessed 2020-10-06]
16. National COVID Cohort Collaborative (N3C) Internet. National Center for Advancing Translational Sciences. URL: https:/
/ncats.nih.gov/n3c [accessed 2020-10-06]
17. The COVID-19 Host Genetics Initiative. COVID-19 hg. URL: https://www.covid19hg.org/ [accessed 2020-10-06]
18. COVID-19 Host Genetics Initiative. The COVID-19 Host Genetics Initiative, a global initiative to elucidate the role of
host genetic factors in susceptibility and severity of the SARS-CoV-2 virus pandemic. Eur J Hum Genet 2020
Jun;28(6):715-718 [FREE Full text] [doi: 10.1038/s41431-020-0636-6] [Medline: 32404885]
19. The COVID-19 Sex-Disaggregated Data Tracker. Global Health 50/50 - The Sex, Gender, and COVID-19 Project. URL:
https://globalhealth5050.org/the-sex-gender-and-covid-19-project/ [accessed 2020-10-06]
20. Lindvall C, Cassel CK, Pantilat SZ, DeCamp M. Ethical considerations in the use of AI mortality predictions in the care
of people with serious illness. Health Affairs. URL: https://www.healthaffairs.org/do/10.1377/hblog20200911.401376/full/
[accessed 2020-10-04]
21. Progress using COVID-19 patient data to train machine learning models for healthcare. University of Cambridge. URL:
https://www.cam.ac.uk/research/news/progress-using-covid-19-patient-data-to-train-machine-learning-models-for-healthcare
[accessed 2020-07-07]
22. Rahmatizadeh S, Valizadeh-Haghi S, Dabbagh A. The role of artificial intelligence in management of critical COVID-19
patients. Journal of Cellular & Molecular Anesthesia 2020 Apr;5(1):16-22. [doi: 10.22037/jcma.v5i1.29752]
23. Grasselli G, Pesenti A, Cecconi M. Critical care utilization for the COVID-19 outbreak in Lombardy, Italy: Early experience
and forecast during an emergency response. JAMA 2020 Apr 28;323(16):1545-1546. [doi: 10.1001/jama.2020.4031]
[Medline: 32167538]
24. Dawson NV, Arkes HR. Systematic errors in medical decision making: judgment limitations. J Gen Intern Med
1987;2(3):183-187. [doi: 10.1007/BF02596149] [Medline: 3295150]
25. Sendak MP, Ratliff W, Sarro D, Alderton E, Futoma J, Gao M, et al. Real-world integration of a sepsis deep learning
technology into routine clinical care: implementation study. JMIR Med Inform 2020 Jul 15;8(7):e15182 [FREE Full text]
[doi: 10.2196/15182] [Medline: 32673244]
26. Verghese A, Shah NH, Harrington RA. What this computer needs is a physician: humanism and artificial intelligence.
JAMA 2018 Jan 02;319(1):19-20. [doi: 10.1001/jama.2017.19198] [Medline: 29261830]
27. Patel BN, Rosenberg L, Willcox G, Baltaxe D, Lyons M, Irvin J, et al. Human-machine partnership with artificial intelligence
for chest radiograph diagnosis. NPJ Digit Med 2019;2:111 [FREE Full text] [doi: 10.1038/s41746-019-0189-7] [Medline:
31754637]
28. Vindegaard N, Benros ME. COVID-19 pandemic and mental health consequences: systematic review of the current evidence.
Brain Behav Immun 2020 Oct;89:531-542 [FREE Full text] [doi: 10.1016/j.bbi.2020.05.048] [Medline: 32485289]
29. Figueroa CA, Aguilera A. The need for a mental health technology revolution in the COVID-19 pandemic. Front Psychiatry
2020;11:523 [FREE Full text] [doi: 10.3389/fpsyt.2020.00523] [Medline: 32581891]
30. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med 2019 Jan;25(1):44-56.
[doi: 10.1038/s41591-018-0300-7] [Medline: 30617339]
31. Panch T, Mattie H, Celi LA. The "inconvenient truth" about AI in healthcare. NPJ Digit Med 2019;2:77 [FREE Full text]
[doi: 10.1038/s41746-019-0155-4] [Medline: 31453372]
32. Lin SY, Mahoney MR, Sinsky CA. Ten ways artificial intelligence will transform primary care. J Gen Intern Med 2019
Aug;34(8):1626-1630 [FREE Full text] [doi: 10.1007/s11606-019-05035-1] [Medline: 31090027]
33. Liu X, Cruz Rivera S, Moher D, Calvert MJ, Denniston AK, SPIRIT-AICONSORT-AI Working Group. Reporting guidelines
for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. Nat Med 2020
Sep;26(9):1364-1374 [FREE Full text] [doi: 10.1038/s41591-020-1034-x] [Medline: 32908283]
34. Cruz Rivera S, Liu X, Chan A, Denniston A, Calvert M, SPIRIT-AICONSORT-AI Working Group, SPIRIT-AICONSORT-AI
Steering Group, SPIRIT-AICONSORT-AI Consensus Group. Guidelines for clinical trial protocols for interventions
https://www.jmir.org/2021/3/e22453 J Med Internet Res 2021 | vol. 23 | iss. 3 | e22453 | p. 8
(page number not for citation purposes)
XSL• FO
RenderXJOURNAL OF MEDICAL INTERNET RESEARCH Santus et al
involving artificial intelligence: the SPIRIT-AI extension. Nat Med 2020 Sep;26(9):1351-1363 [FREE Full text] [doi:
10.1038/s41591-020-1037-7] [Medline: 32908284]
35. Filipp FV. Opportunities for artificial intelligence in advancing precision medicine. Curr Genet Med Rep 2019
Dec;7(4):208-213 [FREE Full text] [doi: 10.1007/s40142-019-00177-4] [Medline: 31871830]
36. Zeggini E, Gloyn AL, Barton AC, Wain LV. Translational genomics and precision medicine: moving from the lab to the
clinic. Science 2019 Sep 27;365(6460):1409-1413. [doi: 10.1126/science.aax4588] [Medline: 31604268]
37. Gruson D, Helleputte T, Rousseau P, Gruson D. Data science, artificial intelligence, and machine learning: opportunities
for laboratory medicine and the value of positive regulation. Clin Biochem 2019 Jul;69:1-7. [doi:
10.1016/j.clinbiochem.2019.04.013] [Medline: 31022391]
38. Suspected COVID-19 pneumonia Diagnosis Aid System. URL: https://intensivecare.shinyapps.io/COVID19/ [accessed
2021-02-19]
39. Feng C, Huang Z, Wang L, Chen X, Zhai Y, Zhu F, et al. A novel triage tool of artificial intelligence assisted diagnosis aid
system for suspected COVID-19 pneumonia in fever clinics. medRxiv. Preprint posted online on March 20, 2020. [doi:
10.1101/2020.03.19.20039099]
40. Jiang X, Coffee M, Bari A, Wang J, Jiang X, Huang J, et al. Towards an artificial intelligence framework for data-driven
prediction of coronavirus clinical severity. Computers, Materials & Continua 2020 Mar;63(1):537-551 [FREE Full text]
[doi: 10.32604/cmc.2020.010691]
41. Freedman AN, Seminara D, Gail MH, Hartge P, Colditz GA, Ballard-Barbash R, et al. Cancer risk prediction models: a
workshop on development, evaluation, and application. J Natl Cancer Inst 2005 May 18;97(10):715-723. [doi:
10.1093/jnci/dji128] [Medline: 15900041]
42. Yala A, Lehman C, Schuster T, Portnoi T, Barzilay R. A deep learning mammography-based model for improved breast
cancer risk prediction. Radiology 2019 Jul;292(1):60-66. [doi: 10.1148/radiol.2019182716] [Medline: 31063083]
43. Hu S, Santus E, Forsyth AW, Malhotra D, Haimson J, Chatterjee NA, et al. Can machine learning improve patient selection
for cardiac resynchronization therapy? PLoS One 2019;14(10):e0222397 [FREE Full text] [doi:
10.1371/journal.pone.0222397] [Medline: 31581234]
44. Wynants L, Van Calster B, Collins GS, Riley RD, Heinze G, Schuit E, et al. Prediction models for diagnosis and prognosis
of covid-19 infection: systematic review and critical appraisal. BMJ 2020 Apr 07;369:m1328 [FREE Full text] [doi:
10.1136/bmj.m1328] [Medline: 32265220]
45. Mei X, Lee H, Diao K, Huang M, Lin B, Liu C, et al. Artificial intelligence-enabled rapid diagnosis of patients with
COVID-19. Nat Med 2020 Aug;26(8):1224-1228 [FREE Full text] [doi: 10.1038/s41591-020-0931-3] [Medline: 32427924]
46. Jin C, Chen W, Cao Y, Xu Z, Zhang X, Deng L, et al. Development and Evaluation of an AI System for COVID-19
Diagnosis. medRxiv. Preprint posted online on June 02, 2020. [doi: 10.1101/2020.03.20.20039834]
47. Schaffter T, Buist DSM, Lee CI, Nikulin Y, Ribli D, Guan Y, the DM DREAM Consortium, et al. Evaluation of combined
artificial intelligence and radiologist assessment to interpret screening mammograms. JAMA Netw Open 2020 Mar
02;3(3):e200265 [FREE Full text] [doi: 10.1001/jamanetworkopen.2020.0265] [Medline: 32119094]
48. Xiao L, Li P, Sun F, Zhang Y, Xu C, Zhu H, et al. Development and validation of a deep learning-based model using
computed tomography imaging for predicting disease severity of coronavirus disease 2019. Front Bioeng Biotechnol
2020;8:898 [FREE Full text] [doi: 10.3389/fbioe.2020.00898] [Medline: 32850746]
49. Clinical management of severe acute respiratory infection (SARI) when COVID-19 disease is suspected. World Health
Organization. 2020 Mar 13. URL: https://www.who.int/docs/default-source/coronaviruse/clinical-management-of-novel-cov.
pdf?sfvrsn=bc7da517_2 [accessed 2021-02-19]
50. NIH harnesses AI for COVID-19 diagnosis, treatment, and monitoring. National Institutes of Health. 2020 Aug 05. URL:
https://www.nih.gov/news-events/news-releases/nih-harnesses-ai-covid-19-diagnosis-treatment-monitoring [accessed
2020-10-06]
51. Yan L, Zhang H, Goncalves J, Xiao Y, Wang M, Guo Y, et al. A machine learning-based model for survival prediction in
patients with severe COVID-19 infection. medRxiv. Preprint posted online on March 17, 2020. [FREE Full text] [doi:
10.1101/2020.02.27.20028027]
52. Senanayake SL. Drug repurposing strategies for COVID-19. Future Drug Discovery 2020 Apr 01;2(2) [FREE Full text]
[doi: 10.4155/fdd-2020-0010]
53. Zhavoronkov A, Aladinskiy V, Zhebrak A, Zagribelnyy B, Terentiev V, Bezrukov D, et al. Potential COVID-2019 3C-like
Protease Inhibitors Designed Using Generative Deep Learning Approaches. ChemRxiv. Preprint posted online on February
11, 2020. [FREE Full text]
54. Gordon DE, Jang GM, Bouhaddou M, Xu J, Obernier K, White KM, et al. A SARS-CoV-2 protein interaction map reveals
targets for drug repurposing. Nature 2020 Jul;583(7816):459-468 [FREE Full text] [doi: 10.1038/s41586-020-2286-9]
[Medline: 32353859]
55. Richardson P, Griffin I, Tucker C, Smith D, Oechsle O, Phelan A, et al. Baricitinib as potential treatment for 2019-nCoV
acute respiratory disease. The Lancet 2020 Feb;395(10223):e30-e31. [doi: 10.1016/s0140-6736(20)30304-4]
https://www.jmir.org/2021/3/e22453 J Med Internet Res 2021 | vol. 23 | iss. 3 | e22453 | p. 9
(page number not for citation purposes)
XSL• FO
RenderXJOURNAL OF MEDICAL INTERNET RESEARCH Santus et al
56. Beck BR, Shin B, Choi Y, Park S, Kang K. Predicting commercially available antiviral drugs that may act on the novel
coronavirus (SARS-CoV-2) through a drug-target interaction deep learning model. Comput Struct Biotechnol J
2020;18:784-790 [FREE Full text] [doi: 10.1016/j.csbj.2020.03.025] [Medline: 32280433]
57. Ostaszewski M, Mazein A, Gillespie ME, Kuperstein I, Niarakis A, Hermjakob H, et al. COVID-19 disease map, building
a computational repository of SARS-CoV-2 virus-host interaction mechanisms. Sci Data 2020 May 05;7(1):136 [FREE
Full text] [doi: 10.1038/s41597-020-0477-8] [Medline: 32371892]
58. Gysi D, Valle ID, Zitnik M, Ameli A, Gan X, Varol O, et al. Network medicine framework for identifying drug repurposing
opportunities for COVID-19. arXiv. Preprint posted online on April 15, 2020. [FREE Full text]
59. Fleming N. How artificial intelligence is changing drug discovery. Nature 2018 May;557(7707):S55-S57. [doi:
10.1038/d41586-018-05267-x] [Medline: 29849160]
60. Stokes JM, Yang K, Swanson K, Jin W, Cubillos-Ruiz A, Donghia NM, et al. A deep learning approach to antibiotic
discovery. Cell 2020 Feb 20;180(4):688-702.e13. [doi: 10.1016/j.cell.2020.01.021] [Medline: 32084340]
61. Senior AW, Evans R, Jumper J, Kirkpatrick J, Sifre L, Green T, et al. Improved protein structure prediction using potentials
from deep learning. Nature 2020 Jan;577(7792):706-710. [doi: 10.1038/s41586-019-1923-7] [Medline: 31942072]
62. Nelson MR, Johnson T, Warren L, Hughes AR, Chissoe SL, Xu C, et al. The genetics of drug efficacy: opportunities and
challenges. Nat Rev Genet 2016 Apr;17(4):197-206. [doi: 10.1038/nrg.2016.12] [Medline: 26972588]
63. Tan-Koi WC, Leow PC, Teo YY. Applications of pharmacogenomics in regulatory science: a product life cycle review.
Pharmacogenomics J 2018 May 22;18(3):359-366. [doi: 10.1038/tpj.2017.47] [Medline: 29205206]
64. Weinshilboum RM, Wang L. Pharmacogenomics: precision medicine and drug response. Mayo Clin Proc 2017
Nov;92(11):1711-1722 [FREE Full text] [doi: 10.1016/j.mayocp.2017.09.001] [Medline: 29101939]
65. Lauschke VM, Ingelman-Sundberg M. Emerging strategies to bridge the gap between pharmacogenomic research and its
clinical implementation. NPJ Genom Med 2020 Mar 05;5(1):9 [FREE Full text] [doi: 10.1038/s41525-020-0119-2] [Medline:
33579994]
66. Silverman EK. Genetics of COPD. Annu Rev Physiol 2020 Feb 10;82:413-431 [FREE Full text] [doi:
10.1146/annurev-physiol-021317-121224] [Medline: 31730394]
67. Severe acute respiratory syndrome coronavirus 2 isolate Wuhan-Hu-1, complete genome. NCBI. URL: https://www.
ncbi.nlm.nih.gov/nuccore/MN908947 [accessed 2020-10-04]
68. Real-time tracking of pathogen evolution - SARS-CoV-2 (COVID-19). Nextstrain. URL: https://nextstrain.org/ [accessed
2021-02-22]
69. Kachuri L, Francis S, Morrison M, Wendt GA, Bossé Y, Cavazos TB, et al. The landscape of host genetic factors involved
in immune response to common viral infections. Genome Med 2020 Oct 27;12(1):93 [FREE Full text] [doi:
10.1186/s13073-020-00790-x] [Medline: 33109261]
70. Benetti E, Tita R, Spiga O, Ciolfi A, Birolo G, Bruselles A, GEN-COVID Multicenter Study, et al. ACE2 gene variants
may underlie interindividual variability and susceptibility to COVID-19 in the Italian population. Eur J Hum Genet 2020
Nov;28(11):1602-1614 [FREE Full text] [doi: 10.1038/s41431-020-0691-z] [Medline: 32681121]
71. Takahashi T, Luzum JA, Nicol MR, Jacobson PA. Pharmacogenomics of COVID-19 therapies. NPJ Genom Med 2020;5:35
[FREE Full text] [doi: 10.1038/s41525-020-00143-y] [Medline: 32864162]
72. Wenham C, Smith J, Morgan R. COVID-19: the gendered impacts of the outbreak. The Lancet 2020 Mar;395(10227):846-848.
[doi: 10.1016/s0140-6736(20)30526-2]
73. Nelson MR, Tipney H, Painter JL, Shen J, Nicoletti P, Shen Y, et al. The support of human genetic evidence for approved
drug indications. Nat Genet 2015 Aug;47(8):856-860. [doi: 10.1038/ng.3314] [Medline: 26121088]
74. Dugger SA, Platt A, Goldstein DB. Drug development in the era of precision medicine. Nat Rev Drug Discov 2018
Mar;17(3):183-196 [FREE Full text] [doi: 10.1038/nrd.2017.226] [Medline: 29217837]
75. Severe Covid-19 GWAS Group, Ellinghaus D, Degenhardt F, Bujanda L, Buti M, Albillos A, et al. Genomewide association
study of severe Covid-19 with respiratory failure. N Engl J Med 2020 Oct 15;383(16):1522-1534 [FREE Full text] [doi:
10.1056/NEJMoa2020283] [Medline: 32558485]
76. Ton A, Gentile F, Hsing M, Ban F, Cherkasov A. Rapid identification of potential inhibitors of SARS-CoV-2 main protease
by deep docking of 1.3 billion compounds. Mol Inform 2020 Aug;39(8):e2000028 [FREE Full text] [doi:
10.1002/minf.202000028] [Medline: 32162456]
77. Abbasi B, Saraf D, Sharma T, Sinha R, Singh S, Gupta P, et al. OSF Preprints. Preprint posted online April 08, 2020. [doi:
10.31219/osf.io/f8zyw]
78. Ong E, Wang H, Wong MU, Seetharaman M, Valdez N, He Y. Vaxign-ML: supervised machine learning reverse vaccinology
model for improved prediction of bacterial protective antigens. Bioinformatics 2020 May 01;36(10):3185-3191. [doi:
10.1093/bioinformatics/btaa119] [Medline: 32096826]
79. Malone B, Simovski B, Moliné C, Cheng J, Gheorghe M, Fontenelle H, et al. Artificial intelligence predicts the immunogenic
landscape of SARS-CoV-2: toward universal blueprints for vaccine designs. bioRxiv. Preprint posted online on April 21,
2020. [FREE Full text] [doi: 10.1101/2020.04.21.052084]
80. Keshavarzi Arshadi A, Webb J, Salem M, Cruz E, Calad-Thomson S, Ghadirian N, et al. Artificial intelligence for COVID-19
drug discovery and vaccine development. Front Artif Intell 2020 Aug 18;3. [doi: 10.3389/frai.2020.00065]
https://www.jmir.org/2021/3/e22453 J Med Internet Res 2021 | vol. 23 | iss. 3 | e22453 | p. 10
(page number not for citation purposes)
XSL• FO
RenderXJOURNAL OF MEDICAL INTERNET RESEARCH Santus et al
81. Hoffmann M, Kleine-Weber H, Schroeder S, Krüger N, Herrler T, Erichsen S, et al. SARS-CoV-2 cell entry depends on
ACE2 and TMPRSS2 and is blocked by a clinically proven protease inhibitor. Cell 2020 Apr 16;181(2):271-280.e8 [FREE
Full text] [doi: 10.1016/j.cell.2020.02.052] [Medline: 32142651]
82. Santus E, Li C, Yala A, Peck D, Soomro R, Faridi N, et al. Do neural information extraction algorithms generalize across
institutions? JCO Clin Cancer Inform 2019 Jul;3:1-8 [FREE Full text] [doi: 10.1200/CCI.18.00160] [Medline: 31310566]
83. Santus E, Schuster T, Tahmasebi AM, Li C, Yala A, Lanahan CR, et al. Exploiting rules to enhance machine learning in
extracting information from multi-institutional prostate pathology reports. JCO Clin Cancer Inform 2020 Oct;4:865-874
[FREE Full text] [doi: 10.1200/CCI.20.00028] [Medline: 33006906]
84. Adnan K, Akbar R. An analytical study of information extraction from unstructured and multidimensional big data. J Big
Data 2019 Oct 17;6:91. [doi: 10.1186/s40537-019-0254-8]
85. Domingo-Fernández D, Baksi S, Schultz B, Gadiya Y, Karki R, Raschka T, et al. COVID-19 Knowledge Graph: a computable,
multi-modal, cause-and-effect knowledge model of COVID-19 pathophysiology. bioRxiv. Preprint posted online on April
15, 2020. [doi: 10.1101/2020.04.14.040667]
86. Cowen L, Ideker T, Raphael BJ, Sharan R. Network propagation: a universal amplifier of genetic associations. Nat Rev
Genet 2017 Sep;18(9):551-562. [doi: 10.1038/nrg.2017.38] [Medline: 28607512]
87. Humayun F, Domingo-Fernández D, Paul George AA, Hopp M, Syllwasschy BF, Detzel MS, et al. A computational
approach for mapping heme biology in the context of hemolytic disorders. Front Bioeng Biotechnol 2020;8:74 [FREE Full
text] [doi: 10.3389/fbioe.2020.00074] [Medline: 32211383]
88. Nelson W, Zitnik M, Wang B, Leskovec J, Goldenberg A, Sharan R. To embed or not: network embedding as a paradigm
in computational biology. Front Genet 2019;10:381 [FREE Full text] [doi: 10.3389/fgene.2019.00381] [Medline: 31118945]
89. Hamilton WL, Ying R, Leskovec J. Representation learning on graphs: methods and applications. IEEE Data Engineering
Bulletin 2017;40(3):52-74 [FREE Full text]
90. KG-Covid-19 Knowledge Graph Hub. GitHub. URL: https://github.com/Knowledge-Graph-Hub/kg-covid-19 [accessed
2021-02-22]
91. COVID-19 Community Project. GitHub. URL: https://github.com/covid-19-net/covid-19-community [accessed 2021-02-22]
92. COVID-KG. GitHub. URL: https://github.com/GillesVandewiele/COVID-KG/ [accessed 2021-02-22]
93. COVID-19 Knowledge Graph. CovidGraph. URL: https://covidgraph.org/ [accessed 2021-02-22]
94. COVID-19 Miner. GitHub. URL: https://github.com/rupertoverall/covid19-miner [accessed 2021-02-22]
95. COVID-19 Biomedical Knowledge Miner. Biomedical Knowledge Miner (BiK>Mi). URL: https://bikmi.
covid19-knowledgespace.de/ [accessed 2021-02-22]
96. COVID-19 Taxila. URL: http://covid19.taxila.io/ [accessed 2021-02-22]
97. COVID-19 Open Research Dataset Challenge (CORD-19). Kaggle (Allen Institute For AI). URL: https://www.kaggle.com/
allen-institute-for-ai/CORD-19-research-challenge [accessed 2020-10-04]
98. The COVID-19 Drug and Gene Set Library. Ma'ayan Laboratory, Computational Systems Biology. URL: https://amp.
pharm.mssm.edu/covid19/ [accessed 2021-02-22]
99. Ristoski P, Rosati J, Di Noia T, De Leone R, Paulheim H. RDF2Vec: RDF graph embeddings and their applications. SW
2019 May 23;10(4):721-752. [doi: 10.3233/sw-180317]
100. COVID-19 SARS-CoV-2 preprints from medRxiv and bioRxiv. URL: https://connect.biorxiv.org/relate/content/181
[accessed 2020-10-04]
101. The Lancet Public Health. COVID-19 puts societies to the test. The Lancet Public Health 2020 May;5(5):e235. [doi:
10.1016/s2468-2667(20)30097-9]
102. Alam F, Dalvi F, Shaar S, Durrani N, Mubarak H, Nikolov A, et al. Fighting the COVID-19 infodemic in social media: a
holistic perspective and a call to arms. arXiv. Preprint posted online on July 15, 2020 [FREE Full text]
103. Song X, Petrak J, Jiang Y, Singh I, Maynard D, Bontcheva K. Classification aware neural topic model and its application
on a new COVID-19 disinformation corpus. arXiv. Preprint posted online on June 5, 2020 [FREE Full text]
104. Li Y, Grandison T, Silveyra P, Douraghy A, Guan X, Kieselbach T, et al. Jennifer for COVID-19: An NLP-powered chatbot
built for the people and by the people to combat misinformation. : Association for Computational Linguistics; 2020 Presented
at: Proceedings of the 1st Workshop on NLP for COVID-19 at ACL 2020; July 2020; Online URL: https://www.aclweb.org/
anthology/2020.nlpcovid19-acl.9
105. The COVID-19 High Performance Computing Consortium. URL: https://covid19-hpc-consortium.org/ [accessed 2021-02-22]
106. Fogel AL, Kvedar JC. Artificial intelligence powers digital medicine. NPJ Digit Med 2018;1:5 [FREE Full text] [doi:
10.1038/s41746-017-0012-2] [Medline: 31304291]
107. Shen B, Yi X, Sun Y, Bi X, Du J, Zhang C, et al. Proteomic and metabolomic characterization of COVID-19 patient sera.
Cell 2020 Jul 09;182(1):59-72.e15 [FREE Full text] [doi: 10.1016/j.cell.2020.05.032] [Medline: 32492406]
108. Ahmed Z, Mohamed K, Zeeshan S, Dong X. Artificial intelligence with multi-functional machine learning platform
development for better healthcare and precision medicine. Database (Oxford) 2020 Jan 01;2020:baaa010 [FREE Full text]
[doi: 10.1093/database/baaa010] [Medline: 32185396]
https://www.jmir.org/2021/3/e22453 J Med Internet Res 2021 | vol. 23 | iss. 3 | e22453 | p. 11
(page number not for citation purposes)
XSL• FO
RenderXYou can also read
